Distributed DataLoader For Pytorch Based On Ray

from torchvision import datasets
from torchvision.transforms import ToTensor
from Dpex import dataloader

training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor()
)
# use DpexDataLoader
train_loader = dataloader.DpexDataLoader(training_data, distribute_mode=True, num_workers=10, batch_size=100, shuffle=True)

for epoch in range(3):
    for index, (image, label) in enumerate(train_loader):
       # your train process
       pass

import torch
import torch.nn as nn
from torch.autograd import Variable
from torch.utils.data import Dataset
from Dpex import dataloader

class MyOwnDataset(Dataset):
     pass
     
# use DpexDataLoader
data_loader = dataloader.DpexDataLoader(dataset=RandomDataset(input_size, data_size),
                                        distribute_mode=True, batch_size=batch_size, shuffle=True, num_workers=10)

class Model(nn.Module):
    pass
    
model = Model()

if torch.cuda.is_available():
    model.cuda()

if torch.cuda.device_count() > 1:
    model = nn.DataParallel(model)

for data in data_loader:
   # train your own model
   pass

import torch
import torch.nn as nn
from torch.utils.data import Dataset
from Dpex.dataloader import DpexDataLoader
from torch.utils.data.distributed import DistributedSampler

# start command: CUDA_VISIBLE_DEVICES=1,6,7 python -m torch.distributed.launch --nproc_per_node=2 pytorch_ddp.py
# 1) 初始化
torch.distributed.init_process_group(backend="nccl")

input_size = 5
output_size = 2
batch_size = 1
data_size = 90000

# 2） 配置每个进程的gpu
local_rank = torch.distributed.get_rank()
torch.cuda.set_device(local_rank)
device = torch.device("cuda", local_rank)

class RandomDataset(Dataset):
    def __init__(self, size, length):
        self.len = length
        self.data = torch.randn(length, size)

    def __getitem__(self, index):
        return self.data[index]

    def __len__(self):
        return self.len

dataset = RandomDataset(input_size, data_size)
# 3）使用DistributedSampler
rand_loader = DpexDataLoader(dataset=dataset, distribute_mode=True, batch_size=batch_size, sampler=DistributedSampler(dataset), num_workers=10)

class Model(nn.Module):
    def __init__(self, input_size, output_size):
        super(Model, self).__init__()
        self.fc = nn.Linear(input_size, output_size)

    def forward(self, input):
        output = self.fc(input)
        print("  In Model: input size", input.size(),
              "output size", output.size())
        return output

model = Model(input_size, output_size)

# 4) 封装之前要把模型移到对应的gpu
model.to(device)

if torch.cuda.device_count() > 1:
    print("Let's use", torch.cuda.device_count(), "GPUs!")
    # 5) 封装
    model = torch.nn.parallel.DistributedDataParallel(model,
                                                      device_ids=[local_rank],
                                                      output_device=local_rank)

for data in rand_loader:
    if torch.cuda.is_available():
        input_var = data
    else:
        input_var = data

    output = model(input_var)
    print("Outside: input size", input_var.size(), "output_size", output.size())